# Can Group Relative Policy Optimization Improve Thai Legal Reasoning and Question Answering?

Source: [Can Group Relative Policy Optimization Improve Thai Legal Reasoning and Question Answering?](<https://www.sota2.com/research/paper/68fa79f71e209131cea80523>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T05:09:30.174Z

Authors: Pawitsapak Akarajaradwong, Chompakorn Chaksangchaichot, Pirat Pothavorn, Attapol Thamrongrattanarit-Rutherford, Ekapol Chuangsuwanich, Sarana Nutanong

Published: 2025-07-13T14:05:48.000Z

## Abstract

The Retrieval-Augmented Generation (RAG) systems' performance on Thai legal question answering is still limited, especially for questions requiring extensive, complex legal reasoning. To address these limitations, we introduce an approach aligning LLMs toward improved law citation accuracy and better response quality using Group-Relative Policy Optimization (GRPO). Our approach leverages BGE-M3 embeddings as a cost-efficient semantic-similarity reward, significantly reducing computational expenses up to 2.5x compared to large language model judges. Experiments on the NitiBench benchmark demonstrate substantial improvements: GRPO achieves up to 90% citation-F1 gains from the base model and a 31% increase in joint quality metrics over instruction tuning. Crucially, our method shows enhanced robustness on complex legal reasoning tasks compared to instruction tuning, providing an effective and resource-efficient solution for enhancing Thai legal LLMs.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2507.09638>)

[PDF](<https://arxiv.org/pdf/2507.09638.pdf>)